Title: Tree Species Traits Determine the Success of LiDAR-Based Crown Mapping in a Mixed Temperate Forest
The ability to automatically delineate individual tree crowns using remote sensing data opens the possibility to collect detailed tree information over large geographic regions. While individual tree crown delineation (ITCD) methods have proven successful in conifer-dominated forests using Light Detection and Ranging (LiDAR) data, it remains unclear how well these methods can be applied in deciduous broadleaf-dominated forests. We applied five automated LiDAR-based ITCD methods across fifteen plots ranging from conifer- to broadleaf-dominated forest stands at Harvard Forest in Petersham, MA, USA, and assessed accuracy against manual delineation of crowns from unmanned aerial vehicle (UAV) imagery. We then identified tree- and plot-level factors influencing the success of automated delineation techniques. There was relatively little difference in accuracy between automated crown delineation methods (51–59% aggregated plot accuracy) and, despite parameter tuning, none of the methods produced high accuracy across all plots (27—90% range in plot-level accuracy). The accuracy of all methods was significantly higher with increased plot conifer fraction, and individual conifer trees were identified with higher accuracy (mean 64%) than broadleaf trees (42%) across methods. Further, while tree-level factors (e.g., diameter at breast height, height and crown area) strongly influenced the success of crown delineations, the influence of plot-level factors varied. The most important plot-level factor was species evenness, a metric of relative species abundance that is related to both conifer fraction and the degree to which trees can fill canopy space. As species evenness decreased (e.g., high conifer fraction and less efficient filling of canopy space), the probability of successful delineation increased. Overall, our work suggests that the tested LiDAR-based ITCD methods perform equally well in a mixed temperate forest, but that delineation success is driven by forest characteristics like functional group, tree size, diversity, and crown architecture. While LiDAR-based ITCD methods are well suited for stands with distinct canopy structure, we suggest that future work explore the integration of phenology and spectral characteristics with existing LiDAR as an approach to improve crown delineation in broadleaf-dominated stands. more »« less
Weinstein, Ben G.; Graves, Sarah J.; Marconi, Sergio; Singh, Aditya; Zare, Alina; Stewart, Dylan; Bohlman, Stephanie A.; White, Ethan P.
(, PLOS Computational Biology)
Grilli, Jacopo
(Ed.)
Broad scale remote sensing promises to build forest inventories at unprecedented scales. A crucial step in this process is to associate sensor data into individual crowns. While dozens of crown detection algorithms have been proposed, their performance is typically not compared based on standard data or evaluation metrics. There is a need for a benchmark dataset to minimize differences in reported results as well as support evaluation of algorithms across a broad range of forest types. Combining RGB, LiDAR and hyperspectral sensor data from the USA National Ecological Observatory Network’s Airborne Observation Platform with multiple types of evaluation data, we created a benchmark dataset to assess crown detection and delineation methods for canopy trees covering dominant forest types in the United States. This benchmark dataset includes an R package to standardize evaluation metrics and simplify comparisons between methods. The benchmark dataset contains over 6,000 image-annotated crowns, 400 field-annotated crowns, and 3,000 canopy stem points from a wide range of forest types. In addition, we include over 10,000 training crowns for optional use. We discuss the different evaluation data sources and assess the accuracy of the image-annotated crowns by comparing annotations among multiple annotators as well as overlapping field-annotated crowns. We provide an example submission and score for an open-source algorithm that can serve as a baseline for future methods.
Balder, Andrew; Anderson, Christopher J; Billor, Nedret
(, Forests)
Tidal freshwater forested wetlands (TFFWs) typically occur at the interface between upriver non-tidal forests and downstream tidal marshes. Due to their location, these forests are susceptible to estuarine and riverine influences, notably periodic saltwater intrusion events. The Mobile-Tensaw (MT) River Delta, one of the largest river deltas in the United States, features TFFWs that are understudied but threatened by sea level rise and human impacts. We surveyed 47 TFFW stands across a tidal gradient previously determined using nine stations to collect continuous water level and salinity data. Forest data were collected from 400 m2 circular plots of canopy and midstory species composition, canopy tree diameter and basal area, stem density, and tree condition. Multivariate hierarchical clustering identified five distinct canopy communities (p = 0.001): Mixed Forest, Swamp Tupelo, Water Tupelo, Bald Cypress, and Bald Cypress and Mixed Tupelo. Environmental factors, such as river distance (p = 0.001) and plot elevation (p = 0.06), were related to community composition. Similar to other TFFWs along the northern Gulf of Mexico, forests closest to Mobile Bay exhibited lower basal areas, species density, diversity, and a higher proportion of visually stressed individual canopy trees compared to those in the upper tidal reach. Results indicate a strong tidal influence on forest composition, structure, and community-level responses.
Franklin, Jerry F; Bell, David M; Remillard, Suzanne M; Pabst, Robert J; Bluhm, Andrew; Powers, Matt
(, Environmental Data Initiative)
A network of more than 130 permanent vegetation plots provides long-term information on patterns and rates of forest succession in most of the major forest zones of the Pacific Northwest. The plot network extends from the coast to the Cascades in western Oregon and Washington and east to ponderosa pine forests in the Oregon Cascades. Most of the permanent plots were established during two intervals: from 1910 to 1948, and from 1970 to 1989. The earlier plots were established by U.S. Forest Service researchers to quantify timber growth in young stands of important commercial species and to help answer other applied forestry questions. The more recent period of plot establishment began under the Coniferous Forest Biome program of the International Biological Program during the 1970s, and continued under the Long-term Ecological Research program. A broader set of objectives motivated plot establishment since 1970, especially quantification of composition, structure, and population and ecosystem dynamics of natural forests. Plots have one of three spatial arrangements: (1) contiguous rectangles subjectively placed within an area of homogeneous forest; (2) circular plots subjectively placed within an area of homogeneous forest; and (3) circular plots systematically located on long transects to sample an entire watershed, ridge, or reserve. Rectangular study areas are mostly 1.0 ha or 0.4 ha (1.0 ac) in size (slope-corrected). Circular plots are 0.1 ha (0.247 ac), not corrected for slope. The tree stratum is the focus of work in closed-forest study areas. All trees larger than a minimum diameter (5 cm for most areas) are permanently tagged. Plots are censused every 5 or 6 years. Attributes measured or assessed at each census include tree diameter, tree vigor, and the condition of the crown and stem. The same attributes are recorded for trees (ingrowth) that have exceeded the minimum diameter since the previous census. In many plots tree locations are surveyed to provide a plot-specific x-y location. A mortality assessment is done for trees that have died since the previous census. The assessment characterizes rooting, stem, and crown condition, obvious signs of distress or disturbance, and the apparent predisposing and proximate causes of tree death.
Franklin, Jerry F; Bell, David M; Remillard, Suzanne M; Pabst, Robert J; Bluhm, Andrew; Powers, Matt
(, Environmental Data Initiative)
A network of more than 130 permanent vegetation plots provides long-term information on patterns and rates of forest succession in most of the major forest zones of the Pacific Northwest. The plot network extends from the coast to the Cascades in western Oregon and Washington and east to ponderosa pine forests in the Oregon Cascades. Most of the permanent plots were established during two intervals: from 1910 to 1948, and from 1970 to 1989. The earlier plots were established by U.S. Forest Service researchers to quantify timber growth in young stands of important commercial species and to help answer other applied forestry questions. The more recent period of plot establishment began under the Coniferous Forest Biome program of the International Biological Program during the 1970s, and continued under the Long-term Ecological Research program. A broader set of objectives motivated plot establishment since 1970, especially quantification of composition, structure, and population and ecosystem dynamics of natural forests. Plots have one of three spatial arrangements: (1) contiguous rectangles subjectively placed within an area of homogeneous forest; (2) circular plots subjectively placed within an area of homogeneous forest; and (3) circular plots systematically located on long transects to sample an entire watershed, ridge, or reserve. Rectangular study areas are mostly 1.0 ha or 0.4 ha (1.0 ac) in size (slope-corrected). Circular plots are 0.1 ha (0.247 ac), not corrected for slope. The tree stratum is the focus of work in closed-forest study areas. All trees larger than a minimum diameter (5 cm for most areas) are permanently tagged. Plots are censused every 5 or 6 years. Attributes measured or assessed at each census include tree diameter, tree vigor, and the condition of the crown and stem. The same attributes are recorded for trees (ingrowth) that have exceeded the minimum diameter since the previous census. In many plots tree locations are surveyed to provide a plot-specific x-y location. A mortality assessment is done for trees that have died since the previous census. The assessment characterizes rooting, stem, and crown condition, obvious signs of distress or disturbance, and the apparent predisposing and proximate causes of tree death.
# Individual Tree Predictions for 100 million trees in the National Ecological Observatory Network Preprint: https://www.biorxiv.org/content/10.1101/2023.10.25.563626v1 ## Manuscript Abstract The ecology of forest ecosystems depends on the composition of trees. Capturing fine-grained information on individual trees at broad scales allows an unprecedented view of forest ecosystems, forest restoration and responses to disturbance. To create detailed maps of tree species, airborne remote sensing can cover areas containing millions of trees at high spatial resolution. Individual tree data at wide extents promises to increase the scale of forest analysis, biogeographic research, and ecosystem monitoring without losing details on individual species composition and abundance. Computer vision using deep neural networks can convert raw sensor data into predictions of individual tree species using ground truthed data collected by field researchers. Using over 40,000 individual tree stems as training data, we create landscape-level species predictions for over 100 million individual trees for 24 sites in the National Ecological Observatory Network. Using hierarchical multi-temporal models fine-tuned for each geographic area, we produce open-source data available as 1km^2 shapefiles with individual tree species prediction, as well as crown location, crown area and height of 81 canopy tree species. Site-specific models had an average performance of 79% accuracy covering an average of six species per site, ranging from 3 to 15 species. All predictions were uploaded to Google Earth Engine to benefit the ecology community and overlay with other remote sensing assets. These data can be used to study forest macro-ecology, functional ecology, and responses to anthropogenic change. ## Data Summary Each NEON site is a single zip archive with tree predictions for all available data. For site abbreviations see: https://www.neonscience.org/field-sites/explore-field-sites. For each site, there is a .zip and .csv. The .zip is a set 1km .shp tiles. The .csv is all trees in a single file. ## Prediction metadata *Geometry* A four pointed bounding box location in utm coordinates. *indiv_id* A unique crown identifier that combines the year, site and geoindex of the NEON airborne tile (e.g. 732000_4707000) is the utm coordinate of the top left of the tile. *sci_name* The full latin name of predicted species aligned with NEON's taxonomic nomenclature. *ens_score* The confidence score of the species prediction. This score is the output of the multi-temporal model for the ensemble hierarchical model. *bleaf_taxa* Highest predicted category for the broadleaf submodel *bleaf_score* The confidence score for the broadleaf taxa submodel *oak_taxa* Highest predicted category for the oak model *dead_label* A two class alive/dead classification based on the RGB data. 0=Alive/1=Dead. *dead_score* The confidence score of the Alive/Dead prediction. *site_id* The four letter code for the NEON site. See https://www.neonscience.org/field-sites/explore-field-sites for site locations. *conif_taxa* Highest predicted category for the conifer model *conif_score* The confidence score for the conifer taxa submodel *dom_taxa* Highest predicted category for the dominant taxa mode submodel *dom_score* The confidence score for the dominant taxa submodel ## Training data The crops.zip contains pre-cropped files. 369 band hyperspectral files are numpy arrays. RGB crops are .tif files. Naming format is __, for example. "NEON.PLA.D07.GRSM.00583_2022_RGB.tif" is RGB crop of the predicted crown of NEON data from Great Smoky Mountain National Park (GRSM), flown in 2022.Along with the crops are .csv files for various train-test split experiments for the manuscript. ### Crop metadata There are 30,042 individuals in the annotations.csv file. We keep all data, but we recommend a filtering step of atleast 20 records per species to reduce chance of taxonomic or data cleaning errors. This leaves 132 species. *score* This was the DeepForest crown score for the crop. *taxonID*For letter species code, see NEON plant taxonomy for scientific name: https://data.neonscience.org/taxonomic-lists *individual*unique individual identifier for a given field record and crown crop *siteID*The four letter code for the NEON site. See https://www.neonscience.org/field-sites/explore-field-sites for site locations. *plotID* NEON plot ID within the site. For more information on NEON sampling see: https://www.neonscience.org/data-samples/data-collection/observational-sampling/site-level-sampling-design *CHM_height* The LiDAR derived height for the field sampling point. *image_path* Relative pathname for the hyperspectral array, can be read by numpy.load -> format of 369 bands * Height * Weight *tile_year* Flight year of the sensor data *RGB_image_path* Relative pathname for the RGB array, can be read by rasterio.open() # Code repository The predictions were made using the DeepTreeAttention repo: https://github.com/weecology/DeepTreeAttentionKey files include model definition for a [single year model](https://github.com/weecology/DeepTreeAttention/blob/main/src/models/Hang2020.py) and [Data preprocessing](https://github.com/weecology/DeepTreeAttention/blob/cae13f1e4271b5386e2379068f8239de3033ec40/src/utils.py#L59).
Hastings, Jack H., Ollinger, Scott V., Ouimette, Andrew P., Sanders-DeMott, Rebecca, Palace, Michael W., Ducey, Mark J., Sullivan, Franklin B., Basler, David, and Orwig, David A. Tree Species Traits Determine the Success of LiDAR-Based Crown Mapping in a Mixed Temperate Forest. Retrieved from https://par.nsf.gov/biblio/10146848. Remote Sensing 12.2 Web. doi:10.3390/rs12020309.
Hastings, Jack H., Ollinger, Scott V., Ouimette, Andrew P., Sanders-DeMott, Rebecca, Palace, Michael W., Ducey, Mark J., Sullivan, Franklin B., Basler, David, & Orwig, David A. Tree Species Traits Determine the Success of LiDAR-Based Crown Mapping in a Mixed Temperate Forest. Remote Sensing, 12 (2). Retrieved from https://par.nsf.gov/biblio/10146848. https://doi.org/10.3390/rs12020309
Hastings, Jack H., Ollinger, Scott V., Ouimette, Andrew P., Sanders-DeMott, Rebecca, Palace, Michael W., Ducey, Mark J., Sullivan, Franklin B., Basler, David, and Orwig, David A.
"Tree Species Traits Determine the Success of LiDAR-Based Crown Mapping in a Mixed Temperate Forest". Remote Sensing 12 (2). Country unknown/Code not available. https://doi.org/10.3390/rs12020309.https://par.nsf.gov/biblio/10146848.
@article{osti_10146848,
place = {Country unknown/Code not available},
title = {Tree Species Traits Determine the Success of LiDAR-Based Crown Mapping in a Mixed Temperate Forest},
url = {https://par.nsf.gov/biblio/10146848},
DOI = {10.3390/rs12020309},
abstractNote = {The ability to automatically delineate individual tree crowns using remote sensing data opens the possibility to collect detailed tree information over large geographic regions. While individual tree crown delineation (ITCD) methods have proven successful in conifer-dominated forests using Light Detection and Ranging (LiDAR) data, it remains unclear how well these methods can be applied in deciduous broadleaf-dominated forests. We applied five automated LiDAR-based ITCD methods across fifteen plots ranging from conifer- to broadleaf-dominated forest stands at Harvard Forest in Petersham, MA, USA, and assessed accuracy against manual delineation of crowns from unmanned aerial vehicle (UAV) imagery. We then identified tree- and plot-level factors influencing the success of automated delineation techniques. There was relatively little difference in accuracy between automated crown delineation methods (51–59% aggregated plot accuracy) and, despite parameter tuning, none of the methods produced high accuracy across all plots (27—90% range in plot-level accuracy). The accuracy of all methods was significantly higher with increased plot conifer fraction, and individual conifer trees were identified with higher accuracy (mean 64%) than broadleaf trees (42%) across methods. Further, while tree-level factors (e.g., diameter at breast height, height and crown area) strongly influenced the success of crown delineations, the influence of plot-level factors varied. The most important plot-level factor was species evenness, a metric of relative species abundance that is related to both conifer fraction and the degree to which trees can fill canopy space. As species evenness decreased (e.g., high conifer fraction and less efficient filling of canopy space), the probability of successful delineation increased. Overall, our work suggests that the tested LiDAR-based ITCD methods perform equally well in a mixed temperate forest, but that delineation success is driven by forest characteristics like functional group, tree size, diversity, and crown architecture. While LiDAR-based ITCD methods are well suited for stands with distinct canopy structure, we suggest that future work explore the integration of phenology and spectral characteristics with existing LiDAR as an approach to improve crown delineation in broadleaf-dominated stands.},
journal = {Remote Sensing},
volume = {12},
number = {2},
author = {Hastings, Jack H. and Ollinger, Scott V. and Ouimette, Andrew P. and Sanders-DeMott, Rebecca and Palace, Michael W. and Ducey, Mark J. and Sullivan, Franklin B. and Basler, David and Orwig, David A.},
}
Warning: Leaving National Science Foundation Website
You are now leaving the National Science Foundation website to go to a non-government website.
Website:
NSF takes no responsibility for and exercises no control over the views expressed or the accuracy of
the information contained on this site. Also be aware that NSF's privacy policy does not apply to this site.
An official website of the United States government
